Keywords: AI/ML Image Reconstruction, AI/ML Image Reconstruction
Motivation: Motion artifacts in multi-modal MRI impair image quality and diagnostic accuracy. Traditional methods handle specific image types but struggle with contrast variations and differing motion patterns [1].
Goal(s): We aim to develop a unified framework to effectively correct motion artifacts in multi-modal MRI.
Approach: We pretrain a CLIP model using MRI volumes and metadata, extracting features that decouple contrast and retain content. These features feed a Transformer to predict motion degradation scores [2]. A Mixture of Experts model allocates weights to specialized networks for final correction [5].
Results: Our method significantly reduces motion artifacts across various MRI, outperforming existing techniques.
Impact: This framework enhances multi-modal MRI by effectively correcting motion artifacts, leading to improved image quality and diagnostic confidence. It holds potential for widespread clinical adoption, benefiting patient care and advancing research involving diverse MRI.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords